Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 663

Liczba wyników na stronie
first rewind previous Strona / 34 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  image processing
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 34 next fast forward last
EN
This paper presents the video-based description method for vehicles passing a detection field. A sequence of source images is created by consecutive frames of the input video stream. The source images are converted into binary target images using the analysis of small gradients. Binary values of the target images represent edges and surfaces comprised in the source images. For all images, the same detection field composed of segments is defined. Inside each segment of the detection field, the sum of edge values is calculated. For the entire detection field, an adjusted sum of the edge values is determined. A vehicle passing the detection field changes the number of edge values within individual segments and the adjusted sum of the edge values for the entire detection field. Vehicle passage through the detection field is described by a discrete function that associates the adjusted sum of the edge values determined for the entire detection field in the current binary image to the ordinal number of the current image in the sequence of source images.
EN
This paper proposes a novel hybrid software/hardware system to automatically create filters for image processing based on genetic algorithms and mathematical morphology. Experimental results show that the hybrid system, implemented using a combination of a NIOS-II processor and a custom hardware accelerator in an Altera FPGA device, is able to generate solutions that are equivalent to the software version in terms of quality in approximately one third of the time.
PL
W artykule zaproponowano nowe hybrydowe oprogramowanie do automatycznego tworzenia filtrów grafiki bazuj ˛acych na algorytmach genetycznych i morfologii matematycznej. Eksperymenty wykazały ˙ze proponowany system wykorzystuj ˛acy procesor NIOS-II i Altera FPGA jest w stanie generowa´c rozwi ˛azanie niemal trzy razy szybciej ni˙z dotychczas stosowane systemy.
EN
The paper presents an evolutionary multi-objective approach to automatically generate morphological filters to solve unknown distances areas, found in depth images used by real-time embedded systems for visually impaired people, and to prevent accidents. It was used Cartesian Genetic Programming as base for the NSGAII multi-objective optimization algorithm proposed to optimize two objectives: low error rates for quality x low complexity for speed. Results showed this approach was able to deliver feasible solutions with good quality and speed to be used in real-time systems.
PL
W artykule zaprezentowano metodę ewolucyjną do automatycznego generowania morfologicznego filtru do określania brakujących danych w obrazach ludzi otrzymywanych on-line. Użyto programu Cartesian Genetic do optymalizacji algorytmu. Zastosowane rozwiązanie umożliwiało dostarczanie poprawę szybkości o dokładności przetwarzania obrazu.
EN
A design method of aspheric fisheye lens has been proposed in this paper, based on the requirements of automobile surround view system. The study has designed a kind of ultra-wide-angle fisheye lens, which only consists of a spherical glass lens and three aspherical plastic lenses. The maximum diameter of imaging aperture is 15. 3 mm; the working distance behind is 2.158 mm; the total length of system is 11.44 mm; the focal length is 0.97 mm; the viewing angle is 210°, and the modulation transfer function (MTF) curve is 0.35 at 60 lp/mm. Furthermore, a kind of a distortion correction algorithm for fisheye lens has been created, which calculates the position of the ideal image point with the actual image point and the obtained distortion curve and distortion model. The algorithm can correct the distorted image taken by a fisheye lens to an image without distortion, which is suitable for the human eye. The algorithm, which is simple and effective, has been applied to the automobile surround view system. It has been verified to be accurate and reasonable, after the comparison is made between the real image taken by a fisheye lens and the corrected image.
EN
The article presents a comparison of original methods of air quality measurement with a professional device Air Smart-box v. 1.2. The methodology consisted of laser beam analysis from the device. To enable detailed photo analysis for the research, an Android mobile application was developed. The OpenCV library was used to process the images. In the article, the hypothesis was put forward that the method using a binary threshold with a threshold value of 50 allows to obtain results closest to those of the station. This hypothesis was confirmed by the results of the experiments.
PL
Artykuł przedstawia porównanie autorskich metod pomiaru jakości powietrza z profesjonalnym urządzeniem Air Smartbox v. 1.2. Metody polegają na analizie zdjęć wiązki lasera w zanieczyszczonym powietrzu. W celu przeprowa-dzenia badań została zaimplementowana aplikacja mobilna, dedykowana na system operacyjny Android, która umożliwia wykonanie zdjęć oraz ich późniejszą obróbkę i analizę. Do przetwarzania obrazów zastosowano bibliotekę OpenCV. W artykule postawiono hipotezę, że metoda wykorzystująca progowanie binarne z wartością progowania wynoszącą 50 pozwala uzyskać wyniki najbardziej zbliżone do wyników ze stacji. Hipoteza ta została potwierdzona uzyskanymi wynikami badań.
EN
The main aim of the presented research was to assess the possibility of utilizing geometric features in object classifica-tion. Studies were conducted using X-ray images of kernels belonging to three different wheat varieties: Kama, Canadi-an and Rosa. As a part of the work, image processing methods were used to determine the main geometric grain parameters, including the kernel area, kernel perimeter, kernel length and kernel width. The results indicate significant differences between wheat varieties, and demonstrates the importance of their size and shape parameters in the classification process. The percentage of correctness of classification was about 92% when the k-Means algorithm was used. A classification rate of 93% was obtain using the K-Nearest Neighbour and Support Vector Machines. Herein, the Rosa variety was better recognized, whilst the Canadian and Kama varieties were less successfully differentiated.
PL
Głównym celem artykułu było zbadanie możliwości wykorzystania cech geometrycznych obiektów w procesie ich klasyfikacji. Materiał badawczy stanowiły zdjęcia rentgenowskie ziaren trzech odmian pszenicy: kama, kanadyjskiej i rosa. W ramach pracy opracowano metody pozwalające na wyznaczenie cech geometrycznych obiektów znajdujących się na obrazach cyfrowych, takich jak długość, szerokość, średnica, pole i obwód. Otrzymane wyniki wykazały istotne różnice pomiędzy parametrami charakteryzującymi kształt i wielkości poszczególnych odmian pszenicy i możliwość ich zastosowania w procesie klasyfikacji. Procent poprawnie zaklasyfikowanych ziaren za pomocą algorytmu k-średnich wynosił 92%. Nieco lepsze wyniki, rzędu 93%, uzyskano za pomocą metod K-najbliższych sąsiadów i wek-torów wspierających. Najlepiej rozróżnialną odmianą okazała się rosa w porównaniu do odmian kanadyjskiej i kama.
EN
We introduce the two-dimensional rational automata (RA) to recognize languages of pictures, as an extension of the finite automata for strings. A RA processes a picture column by column changing its state. The states are columns of symbols, too. The transition function is realized by a transducer. We prove that RA recognize the family REC of languages recognized by tiling systems. Moreover, RA provide a uniform setting for a lot of important notions, techniques and results presented in the last decades for recognizable two-dimensional languages. The model is also very flexible. In fact, there can be imposed restrictions or added features to easily interesting new classes and examples or to capture known families of languages.
EN
In this paper an adaptive median filtering denoising algorithm is proposed to measure yarn diameter and its unevenness. Images of nine different yarn samples were captured using one set of a self-developed yarn image acquisition system. Image separation of the background and yarn sections was conducted using a combination of adaptive median filtering, adaptive threshold segmentation and morphological processing. The noise-free yarn image was used for diameter detection of the subsequent yarn image and the discrimination of the yarn unevenness. Experimental results show that the testing data of yarn unevenness detection based on the adaptive median filter denoising algorithm is very consistent with the data using the traditional method. It is proved that the yarn detection method proposed, based on an adaptive median filter denoising algorithm, is feasible. It can be used to calculate yarn diameter accurately and measure yarn unevenness efficiently, so as to determine the quality of yarn appearance objectively.
PL
W artykule zaproponowano algorytm odszumiania z adaptacyjnym filtrem medianowym (AMF) do pomiaru średnicy przędzy i jej nierówności. Obrazy dziewięciu różnych próbek przędzy zostały przechwycone przy użyciu jednego zestawu samodzielnie opracowanego systemu akwizycji obrazów przędzy. Rozdzielenie obrazu tła i odcinków przędzy przeprowadzono przy użyciu kombinacji AMF, adaptacyjnej segmentacji progowej i przetwarzania morfologicznego. Bezszumowy obraz przędzy wykorzystano do wykrywania średnicy przędzy i rozróżnienia nierówności przędzy. Wyniki eksperymentalne pokazały, że dane testowe dotyczące wykrywania nierówności przędzy w oparciu o zaproponowany algorytm miały wysoką zgodność z danymi uzyskanymi przy użyciu tradycyjnej metody. Algorytmu tego można użyć do dokładnego obliczenia średnicy przędzy i skutecznego pomiaru nierówności przędzy, aby obiektywnie określić jakość wyglądu przędzy.
EN
An objective method for fabric smoothness usually comprises two widely used approaches: 3D laser scanning and 2D image processing, which are represented by GLCM in this work. To make a comparison of them and find out which one is more effective, four 3D parameters (variance, roughness, torsion and interquartile deviation) and eight 2D parameters (mean value and standard deviation of energy, entropy, contrast and correlation) were extracted for AATCC SA replicas and fabrics. Results show that both 3D laser scanning and 2D image processing technology can be used to study smoothness. With regard to accuracy, the 3D laser scanning method is better than the 2D image processing method. Roughness in 3D parameters and the standard deviation of Entropy in 2D parameters have the highest correlation coefficient with the wrinkling grade of replicas, -0.965 and -0.917 respectively. The verification experiment of fabrics proves that roughness can characterise the wrinkling degree better as well. Furthermore, through the work of this paper, we find that the wrinkling degree differences between two adjacent AATCC SA replicas are not the same; the difference between SA-1 and SA-2 is significant, while that between SA-3 and SA-3.5 as well as SA-4 and SA-5 is not so obvious. It is advisable that the AATCC SA replicas for grades 3, 3.5, 4 and 5 be adjusted or improved.
PL
Obiektywna metoda oceny gładkości tkaniny zwykle obejmuje dwa szeroko stosowane podejścia: skanowanie laserowe 3D i przetwarzanie obrazu 2D, które w przedstawionej pracy są reprezentowane przez GLCM. Aby dokonać ich porównania i dowiedzieć się, który sposób jest bardziej skuteczny, wyodrębniono cztery parametry 3D (wariancja, chropowatość, skręcanie i odchylenie międzykwartylowe) i osiem parametrów 2D (wartość średnia i odchylenie standardowe energii, entropia, kontrast i korelacja). Wyniki pokazały, że do badania gładkości można wykorzystać zarówno skanowanie laserowe 3D, jak i technologię przetwarzania obrazu 2D. Pod względem dokładności metoda skanowania laserowego 3D jest lepsza, niż metoda przetwarzania obrazu 2D. Chropowatość parametrów 3D i odchylenie standardowe entropii w parametrach 2D mają najwyższy współczynnik korelacji z klasą marszczenia, odpowiednio -0,965 i -0,917. Eksperyment weryfikacyjny tkanin dowodzi, że szorstkość może lepiej scharakteryzować stopień marszczenia. Ponadto dzięki zaprezentowanym w pracy wynikom stwierdzono, że różnice stopnia marszczenia między dwiema sąsiadującymi replikami AATCC SA nie byłytakie same; różnica między SA-1 i SA-2 była znacząca, podczas gdy różnica między SA-3 i SA-3.5, a także SA-4 i SA-5 nie byłatak oczywista. Wskazane jest, aby repliki AATCC SA dla klas 3, 3.5, 4 i 5 były dostosowane lub ulepszone.
EN
High-quality signal processing of an electrocardiogram (ECG) is an urgent problem in present day diagnostics for revealing dangerous signs of cardiovascular diseases and arrhythmias in patients. The used methods and programs of signal analysis and classification work with the arrays of points for mathematical modeling that must be extracted from an image or recording of an electrocardiogram. The aim of this work is developing a method of extracting images of ECG signals into a one-dimensional array. An algorithm is proposed based on sequential color processing operations and improving the image quality, masking and building a one-dimensional array of points using Python tools and libraries with open access. The results of testing samples from the ECG database and comparing images before and after processing show that the signal extraction accuracy is approximately 95 %. In addition, the presented application design is simple and easy to use. The proposed program for analyzing and processing the ECG data has a great potential in the future for the development of more complex software applications for automatic analyzing the data and determining arrhythmias or other pathologies.
11
Content available remote Fusing fine-tuned deep features for recognizing different tympanic membranes
EN
Otitis media (OM) refers to a group of inflammatory diseases regarding the middle ear. Although there are a wide variety of disease types regarding OM, the most commonly seen disorders are acute otitis media (AOM), otitis media with effusion (OME) and chronic suppurative otitis media (CSOM). The examination of OM in the clinics is realized subjec-tively. This subjective examination is error-prone and leads to a limited variability among specialist. For these reasons, computer-aided systems are in demand. In this study, we focus on recognizing normal, AOM, CSOM, and earwax tympanic membrane (TM) conditions using fused fine-tuned deep features provided by pre-trained deep convolutional neural networks (DCNNs). These features are applied as the input to several networks, such as an artificial neural network (ANN), k-nearest neighbor (k NN), decision tree (DT) and support vector machine (SVM). Moreover, we release a new publicly available TM data set consisting of totally 956 otoscope images. As a result, the DCNNs yielded promising results. Especially, the most efficient results were provided by VGG-16 with an accuracy of 93.05 %. The fused fine-tuned deep features improved the overall classification success. Finally, the proposed model yielded promising results with an accuracy of 99.47 %, sensitivity of 99.35 %, and specificity of 99.77 % using the combination of the fused fine-tuned deep features and SVM model. Consequently, this study shows that fused fine-tuned deep features are rather useful in recognizing different TMs and these features can provide a fully automated model with high sensitivity.
EN
Leukemia is an abnormal proliferation of leukocytes in the bone marrow and blood and it is usually diagnosed by the pathologists by observing the blood smear under a microscope. The count of various cells and their morphological features are used by the pathologists to identify and classify leukemia. An abnormal increase in the count of immature leukocytes along with a reduced count of other blood cells may be an indication of leukemia. The Pathologist may then recommend for bone marrow examination to confirm and identify the specific type of leukemia. These conventional methods are time consuming and may be affected by the skill and expertise of the medical professionals involved in the diagnostic procedures. Image processing based methods can be used to analyze the microscopic smear images to detect the incidence of leukemia automatically and quickly. Image segmentation is one of the very important tasks in processing and analyzing medical images. In the proposed paper an attempt has been made to review the available works in the area of medical image processing of blood smear images, highlighting automated detection of leukemia. The available works in the related area are reviewed based on the segmentation method used. It is learnt that even though there are many studies for detection of acute leukemia only a very few studies are there for the detection of chronic leukemia. There are a few related review studies available in the literature but, none of the works classify the previous studies based on the segmentation method used.
PL
W artykule opisany został problem analizy sceny na obrazach oraz sekwencjach video. Zadanie analizy sceny polega na detekcji, lokalizacji i klasyfikacji obiektów znajdujących się na obrazach. Zaimplementowany system wykorzystuje głęboką sieć neuronową, której struktura oparta została na architekturze YOLO (You Only Look Once). Niskie zapotrzebowania obliczeniowe wybranej architektury pozwala na wykonywanie detekcji w czasie rzeczywistym z zadowalającą dokładnością. W pracy przeprowadzono również badania nad doborem odpowiedniego optymalizatora wykorzystywanego w procesie uczenia. Jako przykładową aplikację wybrano analizę ruchu ulicznego w której skład wchodzi wykrywanie i lokalizacja obiektów takich jak m.in. samochody, motocykle czy sygnalizacja świetlna. Systemy tego typu mogą być wykorzystywane w wszelkiego typu systemach analizy wizyjnej otoczenia np. w pojazdach autonomicznych, systemach automatycznej analizy video z kamer przemysłowych, systemach dozoru czy analizy zdjęć satelitarnych.
EN
The paper describes the problem of scene analysis in images and video sequences. The task of scene analysis is to detect, locate and classify objects in images. As an example of an application, traffic analysis was chosen, which includes the detection and location of objects such as cars, motorcycles or traffic lights. The implemented system uses a deep neural network, whose structure is based on the YOLO (You Only Look Once) architecture. Low computing requirements of the chosen architecture allows performing real-time detection with satisfactory accuracy. The work also included a study on the selection of an appropriate optimizer used in the learning process. The program correctly detects objects with a large surface area, allowing the system to be used in traffic analysis. The work also showed that using the ADAM algorithm allowed significantly shorten the training time of the neural network. Systems of this type can be used in many types of video analysis systems such as autonomous vehicles, automatic video analysis systems with CCTV cameras, surveillance systems or satellite image analysis.
EN
Augmented reality (AR) is a modern technology which integrates 3D virtual objects into the real environment in real time. It can be used for many purposes, which should improve different processes in daily life. The paper will analyze the areas in which this technology is currently used. First, the history of the development of augmented reality will be recalled. Then, this technology will be compared to virtual reality because these terms are often incorrectly used interchangeably. This paper describes the tools and popular platform solutions related to augmented reality. The most common problems related to the use of this technology will be discussed, including popular approaches concerning optical and video combining methods. The existing applications and their potential in solving everyday problems will be analyzed. Finally, the perspectives for the development of augmented reality and its possibilities in the future will be discussed. This paper provides a starting point for using and learning about augmented reality for everyone.
EN
This article presents an analysis of the possibilities of using image processing methods for feature extraction that allows kNN classification based on a ship’s image delivered from an on-water video surveillance system. The subject of the analysis is the Hough transform which enables the detection of straight lines in an image. The recognized straight lines and the information about them serve as features in the classification process. Above all, this approach allows ships to be recognized, which can then be characterized by a specific representation and shape. Recreational units that are often seen on inland waters were classified correctly using this method. Each analyzed camera image was previously prepared – brought to the form where the ship was visible from the side and the background removed (they were monochromatic – white). The results obtained in this work will allow for the development of the final ship classification method based on camera images. This method is a significant part of the emerging system prototype, which is implemented as part of the Automatic Ship Recognition and Identification (SHREC) project.
EN
One of the key methods for diagnosing the structural degradation of technical objects relies on observations of mechanical vibrations that accompany equipment operation and damage. Hardware and software advancements and the development mathematical methods for modelling and inference have increased the popularity of vibroacoustic diagnostics in mechanical systems. Displacement in the time domain of physical points in a vibrating object is the primary diagnostic symptom that undergoes further processing in the measurement system. At present, vibrations are usually registered with the use of accelerometers or optical sensors. Advanced tools for image recording, processing and analysis are deployed in quasi-realistic observations of motion that cannot be perceived by the human senses. This article discusses a method for visualizing vibrations based on deliberate deformation of the registered image through motion magnification. The presented approach is illustrated with selected examples.
17
Content available remote Application of Hybrid Neural Network System in Image Processing
EN
The article describes the use of feedforward two-layer neural network and recursive neural network with feedback, i.e. Hopfield network within a system capable of performing associative memory functions. It has been shown that these structures can be used successfully alone, however, using them together in series in the listed above order significantly improves system performance.
EN
Paper presents the influence of the image resolution on measurement geometric parameters of the objects. Employing as test images the ductile iron structure images allow to analyze the effect of resolution distortion on a model of objects with regular shape. Authors showed on the example images, how decreasing resolution of digital images distorts the value of the parameters describing the shape of the objects, its perimeter and its quantity. The analysis was performed by an automatic algorithm applying image analysis and stereological method.
EN
This article describes the architecture of the Hamming-Lippmann neural network and the math of the modified learning-recognition algorithm and presents some practical aspects for using it for solving an image recognition task. We have created software using C# programming language, that utilized this network as an additional error-correcting procedure, and have solved the task of recognition highly corrupted QR codes (with a connection to the database). Experimental results, of finding the optimal parameters for this algorithm, are presented. This neural network doesn’t require time-consuming computational procedures and large amounts of memory, even for high-resolution and big size images.
PL
W tym artykule opisano architekturę sieci neuronowej Hamminga-Lippmanna oraz matematykę zmodyfikowanego algorytmu rozpoznawania uczenia się, a także przedstawiono kilka praktycznych aspektów korzystania z niej w celu rozwiązania zadania rozpoznawania obrazu. Stworzyliśmy oprogramowanie wykorzystujące język programowania C #, który wykorzystał tę sieć jako dodatkową procedurę korekty błędów i rozwiązaliśmy zadanie rozpoznawania wysoce uszkodzonych kodów QR (w połączeniu z bazą danych). Przedstawiono wyniki eksperymentalne poszukiwania optymalnych parametrów dla tego algorytmu. Opisywana neuronowa nie wymaga czasochłonnych procedur obliczeniowych i dużej ilości pamięci, nawet w przypadku obrazów o wysokiej rozdzielczości i dużych rozmiarach.
EN
Automatic detection of objects is a part of visual systems supporting a quality control system of a manufacturing process. The paper concerns the influence of the resolution of images and the size of detected objects in pixels on measurements results. Test images of the objects of a known size were generated. The values of the perimeter of the objects were compared to the obtained values of measurements on the images with degraded resolution. The process of the degradation of the references images by successive downsizing the resolution, detection and measurements were performed applying automatic algorithm. The analysis of obtained results showed that the size of the analysed objects on the digital images plays an important role in reliability and accuracy of the measurement. The author concludes that, in order to avoid a bias in measurement caused by insufficient object resolution, the minimal acceptable size of objects on digital images in pixels should be recommended.
first rewind previous Strona / 34 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.